import pandas as pd
import plotly.graph_objects as go
from matplotlib import scale

#Import two files, one with weather score for each state and 1 file with accidents per city with coördinates
pf = pd.read_csv('W_PlotData.csv')
df = pd.read_csv('A_AccidentsNewData.csv')

#This code detemines the size of the circles
groottes = [(0, 5), (5, 20), (20, 50), (50, 250), (250, 1000)]
scale = 0.5

#Dates we show
dates = ['2016-01', '2016-04', '2016-07', '2016-10', '2017-01', '2017-04', '2017-07', '2017-10']
fig = go.Figure()

# Loop for the dates that we showcase
for date in dates:
    avg_score_per_state = pf[pf['Date'] == date].groupby('State')['score'].mean().reset_index()
    # The base code for the color of the states that represent weather score
    fig.add_trace(go.Choropleth(
        visible=(date == dates[3]),
        locations=avg_score_per_state['State'],
        z=avg_score_per_state['score'],
        locationmode='USA-states',
        colorscale='PuRd',
        zmin=0.7,
        zmax=1.6,
        colorbar=dict(
            title='Average Weather Score for each state:',
            x=1,
            y=0.3,
            len=0.6,
            thickness=15,
            
        ),
        showscale=True,
        name=f'Weather Score {date}'
    ))

# The base code for the bubbles that represent cities
for lim in groottes:
    scatter_traces = [] 
    for date in dates:
        df_sub = df[(df['Accidents'] >= lim[0]) & (df['Accidents'] < lim[1]) & (df['Date'] == date)]
        scatter_traces.append(go.Scattergeo(
            visible=(date == dates[3]),
            locationmode='USA-states',
            lon=df_sub['lng'],
            lat=df_sub['lat'],
            text=df_sub['City'] + ': ' + df_sub['Accidents'].astype(str) + ' Accidents',
            mode='markers',
            marker=dict(
                size=df_sub['Accidents'] * scale,
                color='#3182bd',
                line_color='rgb(40,40,40)',
                line_width=0.5,
                sizemode='area'
            ),
            name=f'{lim[0]} - {lim[1]} Accidents {date}'
        ))
    fig.add_traces(scatter_traces)

#The code for the slider that selects the date
steps = []
for i, date in enumerate(dates):
    step = dict(
        method='update',
        args=[{'visible': [date == d for d in dates]}],
        label=date
    )
    steps.append(step)

sliders = [dict(
    active=3,
    pad={'t': 20, 'l': 20, 'b':20},
    steps=steps
)]

#Layout opnieuw ingedeeld
fig.update_layout(
    sliders=sliders,
    title='Total of accidents for each city in the USA for 2016 and 2017',
    title_x=0.5,
    title_y=0.95,
    showlegend=True,
    legend_title_text='Amount of Accidents:',
    geo=dict(scope='usa', landcolor='rgb(217, 217, 217)'),
    geo_center=dict(lon=-105, lat=38),
    margin=dict(l=0, r=0, t=50, b=0),
    coloraxis_colorbar=dict(lenmode='fraction', len=0.5),
    dragmode=False,
)

#Knoppen om in en uit te zoomen.
zoom_buttons = [
    dict(args=[{"geo.projection.scale": 1, "geo.center.lon": -105, "geo.center.lat": 38}], label='Back', method="relayout"),
    dict(args=[{"geo.projection.scale": 1.5, "geo.center.lon": -117.5, "geo.center.lat": 44}], label='Zoom Left Top', method="relayout"),
    dict(args=[{"geo.projection.scale": 1.5, "geo.center.lon": -117.5, "geo.center.lat": 31.5}], label='Zoom Left Bottom', method="relayout"),
    dict(args=[{"geo.projection.scale": 1.5, "geo.center.lon": -92.5, "geo.center.lat": 44}], label='Zoom Right Top', method="relayout"),
    dict(args=[{"geo.projection.scale": 1.5, "geo.center.lon": -92.5, "geo.center.lat": 31.5}], label='Zoom Right Bottom', method="relayout")
]

fig.update_layout(
    updatemenus=[dict(type="buttons", showactive=False, buttons=zoom_buttons, x=0.2, y=0.85)],
)

fig.show(config={'scrollZoom': False})

This visualization combines elements of a choropleth and a bubble plot, featuring a time-slide function and zoom controls. It aims to illustrate variations in accident frequency across cities throughout the four seasons of 2016 and 2017. However, the data shows significant disparities in total accidents between seasons, suggesting possible gaps in the dataset or substantial seasonal differences in accident occurrence. Additionally, the weather score does not appear to consistently influence accident numbers. Upon analysis, the map colors fluctuate frequently, particularly noticeable in states like Louisiana (on the right side), where accident rates remain high regardless of weather scores. These factors can potentially lead to misleading interpretations of the data.